© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19807
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èĬ®
    -0.07
    ä¸Ģæ¯Ķ
    -0.06
    eness
    -0.06
    ãģĪãģ°
    -0.06
    ä¸ĢåĬ¨
    -0.06
    rous
    -0.06
    æģ
    -0.05
    é½IJ
    -0.05
    èĥ½æľī
    -0.05
    ako
    -0.05
    POSITIVE LOGITS
    —but
    0.05
    è¾Ľèĭ¦
    0.05
    èī²
    0.05
    æīĢè¬Ĥ
    0.05
    絡
    0.05
    หิà¸Ļ
    0.05
    çĽij管
    0.05
    idental
    0.05
    èĨĬ
    0.05
    identally
    0.05
    Activations Density 0.000%

    No Known Activations